INDEX

Explanations

software development-related terms and coding snippets

oai_token-act-pair · gpt-3.5-turbo

technical terms related to software development

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 arsen

-0.68

 gearing

-0.67

 Murdoch

-0.65

 Unch

-0.64

 intervening

-0.61

 consequential

-0.61

 Mandela

-0.60

 analogue

-0.60

 Mara

-0.60

 Finch

-0.60

POSITIVE LOGITS

tenance

1.24

info

1.23

1.19

data

1.03

scribe

1.01

dragon

0.98

__

0.97

stats

0.95

view

0.95

coins

0.94

Activations Density 0.213%

software development-related terms and coding snippets

technical terms related to software development

No Comments

No Known Activations